A Robust Facial Expression Recognition System for Android Devices
Olaniyi Abiodun AYENI, Samuel Oluwafemi Oluyede, Alowolodu O.D
Corresponding Author : Olaniyi Abiodun AYENI
School of Computing, Federal University Technology Akure, P.M.B 704, Akure, Nigeria
Email ID : email@example.com
Received : 2020-01-15 Accepted : 2020-04-11 Published : 2020-04-14
Abstract : This research work presents an idea for detecting an unknown human face in an input imagery and recognizing the facial expression. The objective of this research is to develop a highly intelligent android application for facial expression recognition. A Facial Expression Recognition system needs to solve the following problems: detection and location of faces in a clustered scene, facial feature extraction, and facial expression classification. In this research work three basic expressions were considered, which are: Happy, Sad, and Angry. Georgia Tech face detection dataset and some locally captured face of Federal University of Technology, Akure students were also used. Local Binary Pattern (LBP) and Random Forest (RF) were used for Feature Extraction and classification respectively for the three emotions. The experiments show that the proposed facial expression recognition framework yields 80% accuracy for angry gesture, 60% for sad gesture and 73.33% for happy gesture.
Keywords : facial expression, detection, recognition, gesture classification and feature extraction.
Citation : Olaniyi Abiodun AYENI et al (2020). A Robust Facial Expression Recognition System for Android Devices, J. of Advancement in Engineering and Technology, V7I3.04. DOI : 10.5281/zenodo.3750534
Copyright : © 2020 Olaniyi Abiodun AYENI. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Journal of Advancement in Engineering and Technology
ISSN : 2348-2931
Volume 7 / Issue 3
ScienceQ Publishing GroupDownload Article
Reviewer Comments : Reviewers comments section of this article will get update shortly.